Track planning method and device, vehicle, storage medium and product
By mapping the vehicle posture information to the reference coordinate system for transformation during trajectory planning, a global coordinate system is obtained for trajectory planning, which solves the problem of poor continuity in trajectory planning and achieves improvements in cost-effectiveness and driving stability.
Patent Information
- Application Number
- CN202410257127.5
- Authority / Receiving Office
- CN · China
- Patent Type
- Applications(China)
- Current Assignee / Owner
- Filing Date
- 2024-03-06
- Publication Date
- 2025-09-09
AI Technical Summary
In the absence of high-precision maps, trajectory planning has poor continuity, resulting in the inability to ensure smooth operation of vehicles in complex scenarios. In addition, high-precision maps and high-precision positioning equipment are expensive.
By acquiring the vehicle posture information at continuous moments, mapping it to a preset reference coordinate system, transforming it to obtain a global coordinate system, and performing trajectory planning within the global coordinate system, the use of high-precision maps and high-precision positioning equipment is avoided.
It achieves trajectory continuity and smoothness, reduces hardware costs, and improves driving stability and safety.
Smart Images
Figure CN120609370A_ABST
Abstract
Description
Technical Field
[0001] The present application relates to the field of trajectory planning technology, and in particular to a trajectory planning method, device, vehicle, storage medium and product. Background Art
[0002] In recent years, with the rapid development of autonomous driving technology, assisted driving systems have been continuously upgraded, and trajectory planning, as an important technology in assisted driving systems, has also been continuously developing.
[0003] Currently, most trajectory planning is based on existing high-precision maps and is performed in a global coordinate system. Some approaches, to save costs or when high-precision maps are unavailable, implement trajectory planning through environmental perception modeling and path planning in a local vehicle coordinate system. However, without an HD map, the surrounding environment can only be perceived in the current frame, and path planning is performed in the current vehicle coordinate system. This makes it impossible to effectively link different frames in trajectory planning, making it difficult to ensure continuity in decision-making and planning, and making it impossible to guarantee smooth vehicle operation in complex scenarios. Summary of the Invention
[0004] This application provides a trajectory planning method, device, vehicle, storage medium and product, aiming to effectively solve technical problems such as high trajectory planning cost and poor continuity.
[0005] According to a first aspect of the present application, the present application provides a trajectory planning method, the method comprising:
[0006] Acquire vehicle posture information at consecutive moments, each piece of vehicle posture information corresponding to a vehicle coordinate system;
[0007] Mapping each vehicle posture information to a preset reference coordinate system to obtain reference posture information at multiple moments;
[0008] transforming the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain a global coordinate system within the continuous moments;
[0009] The trajectory of the vehicle is planned at the current moment in the global coordinate system.
[0010] Furthermore, the reference attitude information includes vehicle position information and yaw angle information;
[0011] The step of transforming the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain the global coordinate system in the continuous moments includes:
[0012] The vehicle coordinate system is translated and / or rotated according to the vehicle position information and the yaw angle information to obtain the global coordinate system.
[0013] Furthermore, the step of translating and / or rotating the vehicle coordinate system according to the vehicle position information and yaw angle information to obtain the global coordinate system includes:
[0014] Calculating a first product between the abscissa of any point in the vehicle coordinate system and the cosine of the yaw angle, calculating a second product between the ordinate of the any point and the sine of the yaw angle, calculating a difference between the first product and the second product, and calculating the sum of the difference and the abscissa in the vehicle position information to obtain the abscissa of the point in the reference coordinate system;
[0015] calculating a third product between the ordinate of the arbitrary point and the cosine value of the yaw angle, calculating a fourth product between the abscissa of the arbitrary point and the sine value of the yaw angle, and calculating a sum of the third product, the fourth product, and the ordinate in the vehicle position information to obtain the ordinate of the point in the reference coordinate system;
[0016] The vehicle coordinate system is rotated / translated using a transformation relationship between the horizontal coordinate and the vertical coordinate of the vehicle coordinate system and the reference coordinate system.
[0017] Furthermore, the step of obtaining vehicle posture information at consecutive moments includes:
[0018] The state change is obtained by calculating the vehicle's last speed information, last yaw angle information, last angular velocity information, and time interval;
[0019] Based on the vehicle's last moment position information, the last moment speed information, the last moment yaw angle information and the last moment angular velocity information, the current moment position information, the current moment speed information, the current moment yaw angle information and the current moment angular velocity information are calculated using the state change amount.
[0020] Furthermore, the step of performing trajectory planning for the vehicle at the current moment in the global coordinate system includes:
[0021] The planned trajectory at the previous moment in the global coordinate system is obtained, and the starting point of the planned trajectory at the current moment is determined from the planned trajectory at the previous moment, and the planned trajectory at the current moment is generated based on the starting point of the planned trajectory at the current moment.
[0022] Furthermore, the preset reference coordinate system is the vehicle coordinate system at the first moment in the vehicle coordinate systems at consecutive moments.
[0023] Furthermore, before obtaining the vehicle posture information at consecutive moments, the method further includes:
[0024] Determine whether to trigger the automatic lane change mode, and when the automatic lane change mode is triggered, obtain vehicle posture information during the continuous automatic lane change time.
[0025] According to a second aspect of the present application, the present application further provides a trajectory planning device, the device comprising:
[0026] A posture information acquisition module is used to acquire vehicle posture information at consecutive moments, each piece of vehicle posture information corresponds to a vehicle coordinate system;
[0027] A reference posture acquisition module, configured to map each vehicle posture information to a preset reference coordinate system to obtain reference posture information at multiple moments;
[0028] A global coordinate establishment module, configured to transform the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain a global coordinate system within the continuous moments;
[0029] The trajectory planning module is used to plan the trajectory of the vehicle at the current moment in the global coordinate system.
[0030] According to a third aspect of the present application, the present application also provides a vehicle comprising the trajectory planning device as described above.
[0031] According to a fourth aspect of the present application, the present application further provides a storage medium, wherein a plurality of instructions are stored in the storage medium, and the instructions are suitable for being loaded by a processor to execute the steps of any of the methods described above.
[0032] According to a fifth aspect of the present application, the present application further provides a computer program product, which implements the steps of any of the above methods when the program code contained in the computer program product is executed by a processor in an electronic device.
[0033] Through one or more embodiments of the above-mentioned embodiments in the present application, at least the following technical effects can be achieved: by converting the vehicle posture information at each moment into a reference coordinate system, and transforming the vehicle coordinate system according to the reference posture information obtained by the conversion, a series of transformed vehicle coordinate systems are obtained. These transformed vehicle coordinate systems are global coordinate systems within continuous moments, that is, short-time global coordinate systems. Trajectory planning is performed on the basis of the short-time global coordinate system, and no high-precision map or high-precision positioning equipment is required in the middle. The vehicle posture information at each moment can be linked, so that the trajectories under the vehicle coordinate system at each moment can be linked, ensuring the continuity of the trajectories at each moment, thereby obtaining a continuous and smooth trajectory, which not only saves the hardware cost of the vehicle but also improves driving stability. BRIEF DESCRIPTION OF THE DRAWINGS
[0034] The following detailed description of the specific embodiments of the present application in conjunction with the accompanying drawings will make the technical solutions and other beneficial effects of the present application apparent.
[0035] Figure 1 Shown is a flow chart of the trajectory planning method provided in an embodiment of the present application;
[0036] Figure 2 The figure shows a schematic diagram of coordinate system transformation provided by an embodiment of the present application;
[0037] Figure 3a The figure shows one of the lane change scenario schematics provided in an embodiment of the present application;
[0038] Figure 3b The figure shows the second lane change scenario diagram provided by the embodiment of the present application;
[0039] Figure 4a The figure shows a schematic diagram of trajectory planning in a local coordinate system provided by an embodiment of the present application;
[0040] Figure 4b The figure shows a schematic diagram of trajectory planning in a short-term global coordinate system provided by an embodiment of the present application;
[0041] Figure 5a Schematic diagram of the estimated trajectory A provided by an embodiment of the present application is shown;
[0042] Figure 5b Schematic diagram of the estimated trajectory B provided by an embodiment of the present application is shown;
[0043] Figure 5c The figure shows one of the actual trajectory diagrams provided in the embodiment of the present application;
[0044] Figure 5d The figure shows the second schematic diagram of the actual trajectory provided by the embodiment of the present application;
[0045] Figure 6 A schematic diagram of the structure of the trajectory planning device provided in an embodiment of the present application. DETAILED DESCRIPTION
[0046] The following will be combined with the accompanying drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the embodiments described are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without making any creative work are within the scope of protection of this application.
[0047] In the description of this application, it should be noted that, unless otherwise specified or limited, the term "and / or" herein is merely a description of an association relationship between associated objects, indicating that three possible relationships exist. For example, "A and / or B" can represent: A exists alone, A and B exist simultaneously, and B exists alone. Furthermore, the character " / " herein, unless otherwise specified, generally indicates that the associated objects are in an "or" relationship.
[0048] At present, autonomous driving systems equipped with high-precision maps and high-precision positioning usually use a global coordinate system for environmental perception modeling, decision-making, and path planning; while assisted driving systems without high-precision maps and high-precision positioning cannot construct a global coordinate system in a time series due to the lack of positioning information, and therefore can only use a real-time local vehicle coordinate system for environmental perception modeling and path planning. However, the cost of autonomous driving systems equipped with high-precision maps and high-precision positioning equipment is too high, and when high-precision maps and high-precision positioning equipment are not equipped, the continuity of trajectory planning cannot be guaranteed. In response to the above problems, this application provides a trajectory planning method. Before describing the trajectory planning method in detail, the technical terms that appear in this application are first explained as follows:
[0049] The vehicle coordinate system is a reference coordinate system relative to the vehicle itself. It typically uses the vehicle's center of mass or axle center as its origin, with the vehicle's forward direction as the positive x-axis. It is also dependent on the vehicle's dimensions and geometry. The vehicle coordinate system can be used to describe information such as the vehicle's position, velocity, acceleration, and attitude (e.g., roll, pitch, and yaw angles).
[0050] A local coordinate system is a coordinate system relative to a reference point or object. In the automotive field, it is typically used to describe the position and attributes of the vehicle's surrounding environment, such as road markings, obstacles, and map data. This reference point or object can be the vehicle itself, a specific point, or other landmark. The origin and coordinate axis directions of the local coordinate system are usually defined relative to this reference point or object. Common local coordinate systems include lane coordinate systems and map coordinate systems.
[0051] A global coordinate system is a reference coordinate system based on the Earth's surface. It uses a three-dimensional coordinate system with a fixed origin and fixed axes to describe the location of points on the Earth. A global coordinate system typically uses longitude, latitude, and altitude (or rectangular coordinates expressed as X, Y, and Z axes) to represent locations. In the automotive field, global coordinate systems are used to describe the vehicle's position on a map and for navigation.
[0052] Figure 1 The figure shows a flow chart of the trajectory planning method provided by the embodiment of the present application. Figure 1 As shown, the trajectory planning method includes the following steps:
[0053] S101, obtaining vehicle posture information at consecutive moments, each piece of vehicle posture information corresponding to a vehicle coordinate system.
[0054] The vehicle posture information includes the vehicle's position, speed, vehicle head orientation, vehicle roll angle, pitch angle, yaw angle, etc. The vehicle posture information at different times corresponds to different vehicle coordinate systems.
[0055] In this step, the vehicle posture information at the previous moment can be used to estimate the vehicle posture information at the current moment. For example, the vehicle posture information can be estimated using the CTRV (Constant Turn Rate and Velocity) model, extended Kalman filter (EKF), particle filter (PF), posture estimation of visual sensors, or multi-sensor fusion. Through continuous iteration, the vehicle posture information at multiple consecutive moments can be finally obtained.
[0056] S102 , mapping each vehicle posture information to a preset reference coordinate system to obtain reference posture information at multiple moments.
[0057] The preset reference coordinate system is the vehicle coordinate system at a specific moment. Typically, the first vehicle coordinate system among multiple consecutive moments is used as the reference coordinate system. Alternatively, the vehicle coordinate system at any given moment can be set as the reference coordinate system based on experience, needs, or performance, and there is no limitation on this.
[0058] In this step, the vehicle's posture information in the vehicle coordinate system is mapped to the reference coordinate system to obtain reference posture information in the reference coordinate system. Each reference posture information corresponds to the vehicle's posture information and also to the vehicle coordinate system at that moment. The reference posture information also includes information such as the vehicle's position, speed, vehicle head orientation, and the vehicle's roll, pitch, and yaw angles.
[0059] S103 , transforming the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain a global coordinate system within the continuous moments.
[0060] In this step, the corresponding vehicle coordinate system is translated and / or rotated according to the reference posture information at each moment, thereby obtaining multiple transformed vehicle coordinate systems. These transformed vehicle coordinate systems constitute a global coordinate system within continuous moments, that is, a short-time global coordinate system.
[0061] S104: Planning a trajectory of the vehicle at the current moment in the global coordinate system.
[0062] In this step, after obtaining the global coordinate system, the vehicle trajectory is planned using a trajectory planning algorithm. This trajectory planning algorithm is a local path planning algorithm and can be based on curve fitting, numerical optimization, DWA, time elastic band, model predictive control, artificial potential field method, rolling window-based local path planning, PRM (Probability Maximum), RRT (Random Tree), and so on.
[0063] The trajectory planning method provided in the embodiment of the present application obtains a series of transformed vehicle coordinate systems by converting the vehicle posture information at each moment into a reference coordinate system and transforming the vehicle coordinate system according to the reference posture information obtained by the conversion. These transformed vehicle coordinate systems are global coordinate systems within continuous moments, that is, short-time global coordinate systems. Trajectory planning is performed on the basis of the short-time global coordinate system. No high-precision map or high-precision positioning equipment is required in the middle, and the vehicle posture information at each moment can be linked, so that the trajectories under the vehicle coordinate system at each moment can be linked, thereby ensuring the continuity of the trajectories at each moment, thereby obtaining a continuous and smooth trajectory, which not only saves the hardware cost of the vehicle but also improves driving stability.
[0064] In some embodiments of the present application, the reference attitude information includes vehicle position information and yaw angle information.
[0065] The step of transforming the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain the global coordinate system in the continuous moments includes:
[0066] The vehicle coordinate system is translated and / or rotated based on the vehicle position information and yaw angle information to obtain the global coordinate system. Specifically, the vehicle coordinate system at each moment is translated and / or rotated using the reference posture information at each moment to obtain a transformed vehicle coordinate system at each moment. These transformed vehicle coordinate systems at each moment constitute the global coordinate system at consecutive moments.
[0067] In some other embodiments of the present application, the step of translating and / or rotating the vehicle coordinate system according to the vehicle position information and yaw angle information to obtain the global coordinate system includes:
[0068] A first product between the horizontal coordinate of any point in the vehicle coordinate system and the cosine value of the yaw angle is calculated, a second product between the vertical coordinate of the any point and the sine value of the yaw angle is calculated, and a difference between the first product and the second product is calculated. The sum of the difference and the horizontal coordinate in the vehicle position information is calculated to obtain the horizontal coordinate of the point in the reference coordinate system.
[0069] Calculate the third product between the longitudinal coordinate of any point and the cosine value of the yaw angle, calculate the fourth product between the transverse coordinate of any point and the sine value of the yaw angle, and calculate the sum of the third product, the fourth product and the longitudinal coordinate in the vehicle position information to obtain the longitudinal coordinate of the point in the reference coordinate system.
[0070] The vehicle coordinate system is rotated / translated using a transformation relationship between the horizontal coordinate and the vertical coordinate of the vehicle coordinate system and the reference coordinate system.
[0071] For example, take the transformation of a vehicle coordinate system as an example, Figure 2 As shown, select any point P'(x',y') in the vehicle coordinate system X'OY', use the vehicle's horizontal axis coordinate and yaw angle in the reference posture information and calculate the horizontal and vertical coordinates (x,y) of the point P corresponding to P' in the reference coordinate system XOY by the following formula:
[0072]
[0073]
[0074] in, is the yaw angle in the reference attitude information at the kth moment, and are the horizontal and vertical coordinates of the vehicle in the reference posture information at the kth moment.
[0075] Thus, a mapping relationship between the point P in the reference coordinate system and the point P' in the vehicle coordinate system is obtained, and the vehicle coordinate system is rotated and translated based on the mapping relationship.
[0076] In some further embodiments of the present application, the step of obtaining vehicle posture information at consecutive moments includes:
[0077] The state change is obtained by calculating the vehicle's last speed information, last yaw angle information, last angular velocity information, and time interval.
[0078] Based on the vehicle's last moment position information, the last moment speed information, the last moment yaw angle information and the last moment angular velocity information, the current moment position information, the current moment speed information, the current moment yaw angle information and the current moment angular velocity information are calculated using the state change amount.
[0079] In this embodiment, the CTRV model is used to estimate the vehicle motion state. Specifically, the vehicle posture information at each moment is estimated using the following formula:
[0080]
[0081] Where xk-1 is the vehicle posture information at time k-1, v k-1 is the speed at time k-1, is the yaw angle at time k-1, is the angular velocity at time k-1, Δt is the time interval between time k and time k-1, x k is the vehicle posture information at time k.
[0082] The vehicle posture information x includes the vehicle's horizontal coordinate p x , vertical coordinate p y , speed v, yaw angle and angular velocity Five dimensions of information, namely
[0083] is the state change of the horizontal axis; is the state change of the vertical axis; is the state change of the yaw angle.
[0084] The vehicle posture information at multiple moments is obtained through multiple iterations, and these vehicle posture information are converted into the reference coordinate system to obtain the reference posture information at multiple moments. Each of the n reference posture information includes
[0085] In some further embodiments of the present application, the step of performing trajectory planning for the vehicle at the current moment in the global coordinate system includes:
[0086] The planned trajectory at the previous moment in the global coordinate system is obtained, and the starting point of the planned trajectory at the current moment is determined from the planned trajectory at the previous moment, and the planned trajectory at the current moment is generated based on the starting point of the planned trajectory at the current moment.
[0087] In this embodiment, after determining the global coordinate system, the planned trajectory at the current moment can select any point on the planned trajectory at the previous moment as the starting point. After determining the starting point and the target end point, the path connecting the starting point and the target end point is generated in the global coordinate system by combining the environmental perception data and using a path rule algorithm. This path usually takes into account factors such as obstacles in the environmental perception data. Further, the generated path is optimized and smoothed to finally obtain a smooth curve trajectory. Schematically, a smooth curve can be generated by a path smoothing algorithm (such as a Bezier curve, a B-spline curve, etc.) and path fitting.
[0088] Among them, the starting point of the planned trajectory at the current moment can be determined from the planned trajectory at the previous moment through artificial potential field method, gradient-based planning algorithm, RRT-connect algorithm, Go-biaing, etc.
[0089] In lane keeping scenarios, the vehicle's driving path is typically a straight line, which is relatively simple. The continuity of each vehicle coordinate system has little impact on the smoothness and continuity of vehicle driving, and vehicle control can be performed directly based on the trajectory generated in the vehicle coordinate system at each moment. However, in complex scenarios such as automatic lane changing, the continuity of each vehicle coordinate system has a significant impact on the smoothness and continuity of vehicle driving, and the above-mentioned trajectory planning method needs to be used to generate the trajectory. Therefore, in some other embodiments of the present application, before obtaining the vehicle posture information at consecutive moments, the method further includes:
[0090] Determine whether to trigger the automatic lane change mode, and when the automatic lane change mode is triggered, obtain vehicle posture information during the continuous automatic lane change time.
[0091] Among them, the automatic lane change mode is automatically triggered by the vehicle based on real-time environmental perception and other information. The automatic lane change scenarios include overtaking and lane changing (such as Figure 3a ), changing lanes at the expressway entrance, changing lanes at the entrance ramp (as shown Figure 3b as shown), changing lanes when the road is blocked, planning and guiding lane changes, etc.
[0092] In this embodiment, the aforementioned trajectory planning method is used to plan and generate trajectories for automatic lane change scenarios in the vehicle's autonomous driving mode. Specifically, when the automatic lane change mode is triggered, the vehicle coordinate system at the trigger moment is used as the reference coordinate system. The vehicle's posture information during the automatic lane change period, starting from the trigger moment and ending at the completion of the lane change, is mapped into the reference coordinate system to obtain reference posture information. This reference posture information is then used to determine the global coordinate system within the automatic lane change period, and the trajectory is then generated within the global coordinate system within the automatic lane change period.
[0093] For example, the trajectory generated in the local coordinate system is compared with the trajectory generated by the above trajectory planning method. Figure 4a It can be seen that in the local coordinate system X v OY v In this case, the trajectory planning of each frame is independent, and the planning starting point can only be planned based on the origin (0, 0) of the vehicle coordinate system at each moment and the yaw angle of 0 degrees. W OY W In this case, the planning starting point of the current frame is selected from the planning trajectory of the previous frame (specifically including the starting point position x, y coordinates and the yaw angle corresponding to the position), so as to obtain Figure 4b As shown in the trajectory, the trajectory planning method provided by this application ensures the continuity of the planning of the previous and next two frames, obtains a smoother planned trajectory, makes the entire trajectory more balanced, and improves the stability of vehicle driving.
[0094] For example, the trajectory generated using the high-precision map and high-precision positioning equipment is used as the real trajectory, the trajectory generated in the local coordinate system is used as the estimated trajectory A, and the trajectory generated using the above-mentioned trajectory planning method is used as the estimated trajectory B.
[0095] contrast Figure 5a The estimated trajectory A in Figure 5b From the estimated trajectory B, we can see that the planning starting point of each frame in the estimated trajectory A is at the vehicle's position, the lane change trajectory of each frame is independent, and the overall trajectory has no continuity; the planning starting point of each frame in the estimated trajectory B is on the trajectory of the previous frame, and the trajectory of the entire lane change process is continuous.
[0096] contrast Figure 5d The real trajectory and Figure 5b It can be seen from the estimated trajectory B in that the trajectory generated by the trajectory planning method provided in the embodiment of the present application is very close to the trajectory generated under the high-precision equipment, and the trajectory planning method provided in the embodiment of the present application has high accuracy.
[0097] above Figures 5a to 5d The results of trajectory planning for each frame during the 6-second automatic lane change are shown, and the planning period is set to 0.1 seconds. Figure 5c The true estimate of is the reference truth value of the estimated trajectory A.
[0098] The trajectory planning method provided in the embodiments of this application transforms the corresponding vehicle coordinate system in an automatic lane change scenario based on the baseline posture information at different times to obtain a global coordinate system within the automatic lane change time. Trajectory planning is then performed within this global coordinate system to obtain a continuous and smooth trajectory, ensuring the vehicle maintains continuity and stability during automatic lane change scenarios. Furthermore, since this trajectory planning process does not require high-precision maps or high-precision positioning equipment, the entire trajectory planning process is relatively low-cost.
[0099] In addition, it should be noted that the automatic lane change time is typically less than 10 seconds. During this time period, the accumulated error in trajectory planning in the short-term global coordinate system is small, sufficient to ensure the accuracy of trajectory planning. In other embodiments, to prevent the accumulated error from being too large, the continuous time is kept within 10 seconds.
[0100] In some other embodiments of the present application, if the vehicle is equipped with a high-precision map and a high-precision positioning device, the high-precision map and the high-precision positioning device can be used to perform trajectory planning in a global coordinate system to obtain trajectory C. At the same time, the above-mentioned trajectory planning method is used to perform trajectory planning in a short-term global coordinate system to obtain trajectory D, and trajectory C and trajectory D are fused to obtain the final trajectory. Alternatively, if the trajectory C generated by the high-precision map and the high-precision positioning device has a large error, trajectory D is used as the final trajectory. The above method can further improve the accuracy of trajectory planning, thereby improving the stability and safety of vehicle driving.
[0101] Based on any of the above embodiments, another embodiment of the present application further provides a trajectory planning device, Figure 6 This is a schematic diagram of the structure of the trajectory planning device provided in this application, such as Figure 6 As shown, the trajectory planning device includes:
[0102] The posture information acquisition module 601 is used to acquire the vehicle posture information at consecutive moments, where each piece of vehicle posture information corresponds to the posture information of the vehicle in the vehicle coordinate system at a moment.
[0103] The reference posture acquisition module 602 is used to map each vehicle posture information to a preset reference coordinate system to obtain reference posture information at multiple moments.
[0104] The global coordinate establishing module 603 is used to transform the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain the global coordinate system within the continuous moments.
[0105] The trajectory planning module 604 is used to plan the trajectory of the vehicle at the current moment in the global coordinate system.
[0106] The trajectory planning device corresponds to the above-mentioned trajectory planning method and will not be described in detail here.
[0107] Based on any of the above embodiments, another embodiment of the present application further provides a vehicle, which is equipped with the above trajectory planning device.
[0108] Based on any of the above embodiments, another embodiment of the present application further provides an electronic device, which may include: a processor, a communication interface, a memory, and a communication bus, wherein the processor, the communication interface, and the memory communicate with each other via the communication bus. The processor can call logic instructions in the memory to execute the above trajectory planning method.
[0109] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0110] In addition, the logical instructions in the above-mentioned memory can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when sold or used as an independent product. Based on this understanding, the technical solution of the present application, or the part that contributes to the prior art, or the part of the technical solution, can be embodied in the form of a software product, which is stored in a storage medium and includes several instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the method described in each embodiment of the present application. The aforementioned storage medium includes: various media that can store program codes, such as a USB flash drive, a mobile hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk or an optical disk.
[0111] On the other hand, an embodiment of the present application further provides a storage medium on which a plurality of instructions are stored, and the instructions are suitable for being loaded by a processor to execute the trajectory planning method provided in the above embodiments.
[0112] On the other hand, an embodiment of the present application further provides a computer program product, which, when the program code contained in the computer program product is executed by a processor in an electronic device, implements the trajectory planning method provided in the above embodiments.
[0113] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate, and the components shown as units may or may not be physical units, i.e., they may be located in one location or distributed across multiple network units. Some or all of the modules may be selected based on actual needs to achieve the objectives of the present embodiment. Persons of ordinary skill in the art will be able to understand and implement the present invention without inventive effort.
[0114] Through the description of the above embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus a necessary general hardware platform, or of course, by hardware. Based on this understanding, the essence of the above technical solution or the part that contributes to the existing technology can be embodied in the form of a software product. The computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a magnetic disk, an optical disk, etc., and includes a number of instructions for enabling a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or certain parts of the embodiments.
[0115] In summary, although the present application has been disclosed as above with preferred embodiments, the above preferred embodiments are not intended to limit the present application. Ordinary technicians in this field can make various changes and modifications without departing from the spirit and scope of the present application. Therefore, the scope of protection of the present application shall be based on the scope defined by the claims.
Claims
1. A trajectory planning method, characterized in that: include: Acquire vehicle posture information at consecutive moments, each piece of vehicle posture information corresponding to a vehicle coordinate system; Mapping each vehicle posture information to a preset reference coordinate system to obtain reference posture information at multiple moments; transforming the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain a global coordinate system within the continuous moments; The trajectory of the vehicle is planned at the current moment in the global coordinate system.
2. The trajectory planning method according to claim 1, wherein: The reference attitude information includes vehicle position information and yaw angle information; The step of transforming the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain the global coordinate system in the continuous moments includes: The vehicle coordinate system is translated and / or rotated according to the vehicle position information and the yaw angle information to obtain the global coordinate system.
3. The trajectory planning method according to claim 2, wherein: The step of translating and / or rotating the vehicle coordinate system according to the vehicle position information and the yaw angle information to obtain the global coordinate system includes: Calculating a first product between the abscissa of any point in the vehicle coordinate system and the cosine of the yaw angle, calculating a second product between the ordinate of the any point and the sine of the yaw angle, calculating a difference between the first product and the second product, and calculating the sum of the difference and the abscissa in the vehicle position information to obtain the abscissa of the point in the reference coordinate system; calculating a third product between the ordinate of the arbitrary point and the cosine value of the yaw angle, calculating a fourth product between the abscissa of the arbitrary point and the sine value of the yaw angle, and calculating a sum of the third product, the fourth product, and the ordinate in the vehicle position information to obtain the ordinate of the point in the reference coordinate system; The vehicle coordinate system is rotated / translated using a transformation relationship between the horizontal coordinate and the vertical coordinate of the vehicle coordinate system and the reference coordinate system.
4. The trajectory planning method according to claim 1, wherein: The step of obtaining vehicle posture information at consecutive moments includes: The state change is obtained by calculating the vehicle's last speed information, last yaw angle information, last angular velocity information, and time interval; Based on the vehicle's last moment position information, the last moment speed information, the last moment yaw angle information and the last moment angular velocity information, the current moment position information, the current moment speed information, the current moment yaw angle information and the current moment angular velocity information are calculated using the state change amount.
5. The trajectory planning method according to claim 1, wherein: The step of performing trajectory planning for the vehicle at the current moment in the global coordinate system includes: The planned trajectory at the previous moment in the global coordinate system is obtained, and the starting point of the planned trajectory at the current moment is determined from the planned trajectory at the previous moment, and the planned trajectory at the current moment is generated based on the starting point of the planned trajectory at the current moment.
6. The trajectory planning method according to claim 1, wherein: The preset reference coordinate system is the vehicle coordinate system at the first moment in the vehicle coordinate systems at consecutive moments.
7. The trajectory planning method according to claim 1, wherein: Before acquiring the vehicle posture information at consecutive moments, the method further includes: Determine whether to trigger the automatic lane change mode, and when the automatic lane change mode is triggered, obtain vehicle posture information during the continuous automatic lane change time.
8. A trajectory planning device, characterized in that: The device comprises: A posture information acquisition module is used to acquire vehicle posture information at consecutive moments, each piece of vehicle posture information corresponds to a vehicle coordinate system; A reference posture acquisition module, configured to map each vehicle posture information to a preset reference coordinate system to obtain reference posture information at multiple moments; A global coordinate establishment module, configured to transform the corresponding vehicle coordinate system according to the reference posture information at different moments to obtain a global coordinate system within the continuous moments; The trajectory planning module is used to plan the trajectory of the vehicle at the current moment in the global coordinate system.
9. A vehicle, characterized in that: Comprising the trajectory planning device as claimed in claim 8.
10. A storage medium, characterized in that: The storage medium stores a plurality of instructions, which are suitable for being loaded by a processor to execute the steps of the method according to any one of claims 1 to 7.
11. A computer program product, characterized in that When the program code contained in the computer program product is executed by a processor in an electronic device, the steps of the method according to any one of claims 1 to 7 are implemented.